© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 51990
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stronger
    0.45
     inelastic
    0.43
     Sulfur
    0.41
     sharper
    0.40
    癥
    0.40
    olica
    0.40
     volv
    0.39
    咲
    0.39
     evapor
    0.39
    𒊒
    0.38
    POSITIVE LOGITS
    /
    0.38
     org
    0.37
    izards
    0.36
    }));
    0.35
    indows
    0.34
     PMC
    0.34
     attend
    0.33
    rng
    0.33
     الصي
    0.33
     proguardFiles
    0.32
    Activations Density 0.000%

    No Known Activations